arXiv subjects

Laurent Caraffa

Publications and source records attributed to Laurent Caraffa.

11 recordsLinked to original sources

arXiv2026

Cyclone: Diffusion Model for Cycle-Consistent Weather Editing from Unpaired Driving Data

Reliable perception under diverse weather conditions remains a major challenge for autonomous driving systems. A common strategy to improve robustness is either to synthesize adverse weather conditions for training perception models or to apply weather-removal techniques to recover clean inputs. However, existing approaches typically rely on synthetic data augmentation or physics-based, task-specific models that require paired training data and often struggle to generate realistic weather effects or generalize robustly to out-of-domain scenarios. Toward this problem, we present Cyclone, a unified framework for weather editing based on latent diffusion, equipped with cycle-consistent constraints and knowledge from image-text models. Cyclone enables the generation of multiple weather conditions across diverse scenes while eliminating the need for paired data. Experimental results show that our approach produces more realistic, structure-preserving outputs than existing baselines and leads to consistent improvements across several downstream driving perception tasks. Furthermore, we demonstrate that Cyclone can be distilled to a video diffusion model for temporally consistent weather editing.

cs.CV↗

arXiv2026

A Transport-Based Geometry of Belief-Cost

A finite agent, a machine's digital twin or any bounded reasoner, infers a fixed and noisy world through finite sensors, so its coherent output is a belief: a probability density over states (the Bayes posterior). Such an agent stops short of certainty, and revising a belief carries a cost. We propose a framework for belief costs based on optimal transport, motivated by these facts. We pose two postulates. P0 (the arena): a revision cost is a scalar price on optimal transport, so beliefs live in Wasserstein space. P1 (uniform pricing): one nat of knowledge costs the same metric length everywhere, the eikonal condition. Among conceivable pricing rules we study this one. Under P0 and P1 the cost metric is optimal transport conformally reweighted by Fisher information, $\tilde g_{e,U}=2(e+U)\,g_{W_2}$, and the Fisher family is a characterization: among continuous reliefs, uniform pricing is equivalent to $U=cJ$. Two consequences follow on the conformal class. Certainty sits at infinite cost-distance once the relief dominates the Fisher information, so a well-posed inference has a cost floor diverging at certainty (necessity conjectural beyond power laws). On location-scale leaves the geometry is hyperbolic, and the Stam bound places the Gaussian as the most curved one (at $e=0$). The results are geometric, in nats, and hold up to units: a change of cost unit rescales all distances and preserves every conclusion (boundary, eikonal family, hyperbolicity, Gaussian extremum), a gauge theorem; a global change of state units at $e=0$ is an isometry; the content lies in signs, rankings and ratios. Via Landauer (one nat worth $k_BT$) the cost floor becomes an energy floor: revising toward certainty would demand unbounded energy. Physics anchors the unit and enters no theorem. Removing either postulate leaves the selection open.

cs.LG↗

arXiv2026

SEM-ROVER: Semantic Voxel-Guided Diffusion for Large-Scale Driving Scene Generation

Scalable generation of outdoor driving scenes requires 3D representations that remain consistent across multiple viewpoints and scale to large areas. Existing solutions either rely on image or video generative models distilled to 3D space, harming the geometric coherence and restricting the rendering to training views, or are limited to small-scale 3D scene or object-centric generation. In this work, we propose a 3D generative framework based on $Σ$-Voxfield grid, a discrete representation where each occupied voxel stores a fixed number of colorized surface samples. To generate this representation, we train a semantic-conditioned diffusion model that operates on local voxel neighborhoods and uses 3D positional encodings to capture spatial structure. We scale to large scenes via progressive spatial outpainting over overlapping regions. Finally, we render the generated $Σ$-Voxfield grid with a deferred rendering module to obtain photorealistic images, enabling large-scale multiview-consistent 3D scene generation without per-scene optimization. Extensive experiments show that our approach can generate diverse large-scale urban outdoor scenes, renderable into photorealistic images with various sensor configurations and camera trajectories while maintaining moderate computation cost compared to existing approaches.

cs.CV↗

arXiv2026

Fused-Planes: Why Train a Thousand Tri-Planes When You Can Share?

Tri-Planar NeRFs enable the application of powerful 2D vision models for 3D tasks, by representing 3D objects using 2D planar structures. This has made them the prevailing choice to model large collections of 3D objects. However, training Tri-Planes to model such large collections is computationally intensive and remains largely inefficient. This is because the current approaches independently train one Tri-Plane per object, hence overlooking structural similarities in large classes of objects. In response to this issue, we introduce Fused-Planes, a novel object representation that improves the resource efficiency of Tri-Planes when reconstructing object classes, all while retaining the same planar structure. Our approach explicitly captures structural similarities across objects through a latent space and a set of globally shared base planes. Each individual Fused-Planes is then represented as a decomposition over these base planes, augmented with object-specific features. Fused-Planes showcase state-of-the-art efficiency among planar representations, demonstrating $7.2 \times$ faster training and $3.2 \times$ lower memory footprint than Tri-Planes while maintaining rendering quality. An ultra-lightweight variant further cuts per-object memory usage by $1875 \times$ with minimal quality loss. Our project page can be found at https://fused-planes.github.io .

cs.CV↗

arXiv2026

Dissipative Learning: A Framework for Viable Adaptive Systems

We propose a perspective in which learning is an intrinsically dissipative process. Forgetting and regularization are not heuristic add-ons but structural requirements for adaptive systems. Drawing on information theory, thermodynamics, and information geometry, we introduce the BEDS (Bayesian Emergent Dissipative Structures) framework, modeling learning as the evolution of compressed belief states under dissipation constraints. A central contribution is the Conditional Optimality Theorem, showing that Fisher-Rao regularization measuring change via information divergence rather than Euclidean distance is the unique thermodynamically optimal regularization strategy, achieving minimal dissipation. Euclidean regularization is shown to be structurally suboptimal. The framework unifies existing methods (Ridge, SIGReg, EMA, SAC) as special cases of a single governing equation. Within this view, overfitting corresponds to over-crystallization, while catastrophic forgetting reflects insufficient dissipation control. The framework distinguishes BEDS-crystallizable problems, where beliefs converge to stable equilibria, from BEDS-maintainable problems, which require continual adaptation. It extends naturally to continual and multi-agent systems, where viability, stability under adaptation and finite resources replaces asymptotic optimality as the primary criterion. Overall, this work reframes learning as maintaining viable belief states under dissipation constraints, providing a principled lens on forgetting, regularization, and stability.

cs.LG↗

arXiv2026

Thermodynamically Optimal Regularization under Information-Geometric Constraints

Modern machine learning relies on a collection of empirically successful but theoretically heterogeneous regularization techniques, such as weight decay, dropout, and exponential moving averages. At the same time, the rapidly increasing energetic cost of training large models raises the question of whether learning algorithms approach any fundamental efficiency bound. In this work, we propose a unifying theoretical framework connecting thermodynamic optimality, information geometry, and regularization. Under three explicit assumptions -- (A1) that optimality requires an intrinsic, parametrization-invariant measure of information, (A2) that belief states are modeled by maximum-entropy distributions under known constraints, and (A3) that optimal processes are quasi-static -- we prove a conditional optimality theorem. Specifically, the Fisher--Rao metric is the unique admissible geometry on belief space, and thermodynamically optimal regularization corresponds to minimizing squared Fisher--Rao distance to a reference state. We derive the induced geometries for Gaussian and circular belief models, yielding hyperbolic and von Mises manifolds, respectively, and show that classical regularization schemes are structurally incapable of guaranteeing thermodynamic optimality. We introduce a notion of thermodynamic efficiency of learning and propose experimentally testable predictions. This work provides a principled geometric and thermodynamic foundation for regularization in machine learning.

cs.LG↗

arXiv2026

BEDS : Bayesian Emergent Dissipative Structures : A Formal Framework for Continuous Inference Under Energy Constraints

We introduce BEDS (Bayesian Emergent Dissipative Structures), a formal framework for analyzing inference systems that must maintain beliefs continuously under energy constraints. Unlike classical computational models that assume perfect memory and focus on one-shot computation, BEDS explicitly incorporates dissipation (information loss over time) as a fundamental constraint. We prove a central result linking energy, precision, and dissipation: maintaining a belief with precision $τ$ against dissipation rate $γ$ requires power $P \geq γk_{\rm B} T / 2$, with scaling $P \propto γ\cdot τ$. This establishes a fundamental thermodynamic cost for continuous inference. We define three classes of problems -- BEDS-attainable, BEDS-maintainable, and BEDS-crystallizable -- and show these are distinct from classical decidability. We propose the Gödel-Landauer-Prigogine conjecture, suggesting that closure pathologies across formal systems, computation, and thermodynamics share a common structure.

cs.CV↗

arXiv2025

Pointmap-Conditioned Diffusion for Consistent Novel View Synthesis

Synthesizing extrapolated views remains a difficult task, especially in urban driving scenes, where the only reliable sources of data are limited RGB captures and sparse LiDAR points. To address this problem, we present PointmapDiff, a framework for novel view synthesis that utilizes pre-trained 2D diffusion models. Our method leverages point maps (i.e., rasterized 3D scene coordinates) as a conditioning signal, capturing geometric and photometric priors from the reference images to guide the image generation process. With the proposed reference attention layers and ControlNet for point map features, PointmapDiff can generate accurate and consistent results across varying viewpoints while respecting geometric fidelity. Experiments on real-life driving data demonstrate that our method achieves high-quality generation with flexibility over point map conditioning signals (e.g., dense depth map or even sparse LiDAR points) and can be used to distill to 3D representations such as 3D Gaussian Splatting for improving view extrapolation.

cs.CV↗

arXiv2025

RefinedFields: Radiance Fields Refinement for Planar Scene Representations

Planar scene representations have recently witnessed increased interests for modeling scenes from images, as their lightweight planar structure enables compatibility with image-based models. Notably, K-Planes have gained particular attention as they extend planar scene representations to support in-the-wild scenes, in addition to object-level scenes. However, their visual quality has recently lagged behind that of state-of-the-art techniques. To reduce this gap, we propose RefinedFields, a method that leverages pre-trained networks to refine K-Planes scene representations via optimization guidance using an alternating training procedure. We carry out extensive experiments and verify the merit of our method on synthetic data and real tourism photo collections. RefinedFields enhances rendered scenes with richer details and improves upon its base representation on the task of novel view synthesis. Our project page can be found at https://refinedfields.github.io .

cs.CV↗

arXiv2025

Bringing NeRFs to the Latent Space: Inverse Graphics Autoencoder

While pre-trained image autoencoders are increasingly utilized in computer vision, the application of inverse graphics in 2D latent spaces has been under-explored. Yet, besides reducing the training and rendering complexity, applying inverse graphics in the latent space enables a valuable interoperability with other latent-based 2D methods. The major challenge is that inverse graphics cannot be directly applied to such image latent spaces because they lack an underlying 3D geometry. In this paper, we propose an Inverse Graphics Autoencoder (IG-AE) that specifically addresses this issue. To this end, we regularize an image autoencoder with 3D-geometry by aligning its latent space with jointly trained latent 3D scenes. We utilize the trained IG-AE to bring NeRFs to the latent space with a latent NeRF training pipeline, which we implement in an open-source extension of the Nerfstudio framework, thereby unlocking latent scene learning for its supported methods. We experimentally confirm that Latent NeRFs trained with IG-AE present an improved quality compared to a standard autoencoder, all while exhibiting training and rendering accelerations with respect to NeRFs trained in the image space. Our project page can be found at https://ig-ae.github.io .

cs.CV↗

arXiv2024

Exploring 3D-aware Latent Spaces for Efficiently Learning Numerous Scenes

We present a method enabling the scaling of NeRFs to learn a large number of semantically-similar scenes. We combine two techniques to improve the required training time and memory cost per scene. First, we learn a 3D-aware latent space in which we train Tri-Plane scene representations, hence reducing the resolution at which scenes are learned. Moreover, we present a way to share common information across scenes, hence allowing for a reduction of model complexity to learn a particular scene. Our method reduces effective per-scene memory costs by 44% and per-scene time costs by 86% when training 1000 scenes. Our project page can be found at https://3da-ae.github.io .

cs.CV↗